Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.
☆245Sep 13, 2026Updated 2 months ago
Alternatives and similar repositories for agent-audit
Users that are interested in agent-audit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- CatchBench: a benchmark for auditing agent failures across the full lifecycle.☆12Updated this week
- ☆40Jun 13, 2026Updated 5 months ago
- A curated list of PhD, RA, and Intern openings in Computer Science (CS), Electrical & Computer Engineering (ECE), and Artificial Intellig…☆22Sep 1, 2025Updated last year
- Official codebase for the paper "Auditing Agent Harness Safety"☆59Oct 12, 2026Updated last month
- Audit any agent decision across its past, present, and future, on one typed graph.☆31Updated this week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 6 months ago
- Official inference code for C-SafeQA, a policy-grounded benchmark for response-level Chinese safety evaluation of LLMs and automated safe…☆24Nov 2, 2026Updated 2 weeks ago
- Static scanner for MCP-connected AI agent pipelines. 501 rules across 14 categories, 14 compliance frameworks, OWASP Agentic 10/10 + MCP …☆12Updated this week
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆53Jun 1, 2026Updated 5 months ago
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks☆101Nov 7, 2026Updated last week
- Official implementation of the paper "AWM: Accurate Weight-Matrix Fingerprint for Large Language Models"☆13Feb 20, 2026Updated 8 months ago
- A modern SaaS platform for renewable material construction management. Features AI-powered blueprint generation, real-time factory monito…☆12Mar 7, 2026Updated 8 months ago
- ☆28Nov 4, 2026Updated last week
- 1,017 system prompts from real AI products, audited span by span against the eight AISPA assurance dimensions☆37Oct 13, 2026Updated last month
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [COLM 2025] JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model☆27Nov 25, 2025Updated 11 months ago
- Auditing AI agents: a curated list of papers, tools, datasets, benchmarks, and standards covering reliability, monitoring, failure attrib…☆161Nov 10, 2026Updated last week
- A Julia Library for Outlier Detection (Anomaly Detection)☆11Sep 1, 2018Updated 8 years ago
- Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedbac…☆87Nov 5, 2026Updated last week
- A local, rule-based security guard for DeepSeek Harness agents. It hooks agent tool calls and prompt assembly and applies a policy table …☆26Sep 17, 2026Updated 2 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆1,041Jun 2, 2026Updated 5 months ago
- One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (…☆262Updated this week
- “ToolHazard: Scalable Red Teaming of LLM Agents via Adversarial Tool-Interactive Environment and Task Synthesis”☆15Aug 18, 2026Updated 2 months ago
- Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.☆15Nov 2, 2026Updated 2 weeks ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆69Jan 15, 2026Updated 10 months ago
- A Framework for Evaluating AI Agent Safety in Realistic Environments☆39Aug 10, 2026Updated 3 months ago
- Personal agent configuration for Codex and Claude Code. Not intended for general use.☆16Updated this week
- [ICLR 2026] The official code for "Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models"☆32Feb 7, 2026Updated 9 months ago
- Source code for the ACL'2025 paper titled "Unveiling privacy risks in llm agent memory"☆37Dec 2, 2025Updated 11 months ago
- MCTS (Model Context Threat Scanner) is a local-first security scanner for MCP servers -- static and live tool discovery, multiple analyze…☆31Sep 8, 2026Updated 2 months ago
- Static security auditor for AI-agent configuration: Claude Code, MCP servers, Cursor, Codex, Copilot, Gemini CLI and more. SARIF output, …☆27Updated this week
- ☆38Jul 1, 2026Updated 4 months ago
- ☆50Dec 9, 2025Updated 11 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Static security scanner for AI agents. Catches prompt injection, runaway loops, missing oversight, and compliance gaps across 21 framewor…☆31Nov 1, 2026Updated 2 weeks ago
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆40Jul 31, 2026Updated 3 months ago
- Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Loca…☆15Updated this week
- OpenVul: An Open-Source Post-Training Framework for LLM-Based Vulnerability Detection☆54May 2, 2026Updated 6 months ago
- ☆71Jul 16, 2026Updated 4 months ago
- An autonomous LLM-agent for large-scale, repository-level code auditing☆457Mar 12, 2026Updated 8 months ago
- SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement☆83Jun 11, 2026Updated 5 months ago
Are these results useful?